Short-term power load forecasting can accurately evaluate the change of the whole power load in coal mine,and ensure the safe and reliable operation of the power supply system in coal mine.Due to the influence of many factors,it is difficult to achieve accurate prediction of coal mine electric load prediction.To solve this problem,this paper proposes a short-term mine electric load prediction method based on deep learning theory,which combines convolutional neural network(CNN)and bidirec-tional gated cycle unit(BiGRU),and applies it to the actual coal mine electric load prediction.Firstly,the hybrid learning model of coal mine power load forecasting is constructed.Then,the data processing method is given,the model evaluation index is designed,the simulation platform is built,and a variety of algorithms are analyzed and compared.Finally,based on the configuration software,the power monito-ring and forecasting system is developed and applied to the actual monitoring of coal mine.The field test shows that the proposed method can accurately predict the short-term power load of the mine and pro-vide accurate decision support for the safe operation of the coal mine power system.
deep learningshort-term load forecastingcoal mine power supplyBiGRUmonitoring platform
维普
万方数据
